基于径向曲线与支持向量回归的颅骨修复方法

颅骨修复技术是对有缺损的颅骨补全对应的缺损部分，进而实现颅骨形状的完整性。针对高维颅骨数据，采用径向曲线来表示颅骨几何特征，结合最小二乘支持向量回归的方法构建颅骨修复模型。提取完整的三维颅骨模型的径向曲线，将其分为已有径向曲线和缺失径向曲线两部分作为训练样本，采用最小二乘支持向量回归统计模型复原出待修复颅骨的缺失径向曲线，进而合并生成待修复颅骨的完整径向曲线，通过迭代最近点算法将合并的颅骨径向曲线与颅骨统计模型进行匹配生成完整的三维颅骨模型。实验结果表明，该方法的平均误差达到6.834×10^-3，比主成分分析方法降低2.90倍，具有更好的修复效果。

Skull Restoration Method Based on Radial Curve and Support Vector Regression

The skull restoration technology is to restore the missing parts of a defected skull to make it complete.For high-dimensional skull data, radial curves are used to represent the geometric features of the skull, and on this basis, a skull restoration model is constructed by using the method of least square support vector regression.The radial curves of the complete three-dimensional skull model are extracted as training data, which is divided into two parts:the existing radial curves and the missed radial curves.Then the Least Squares Support Vector Regression(LSSVR) statistical model is used to restore the missed radial curves of the to-be-repaired skull, and the curves are integrated to generate the complete radial curve of the to-be-repaired skull.Finally, the Iterative Closest Point(ICP) algorithm is used to match the generated radial curve of the skull with the statistical model of the skull to generate a complete three-dimensional skull model.The experimental results show that the average error of this method reaches 6.834×10^-3, which is 2.90 times lower than that of the Principal Component Analysis(PCA) method, displaying better restoration performance.